Hacker News new | ask | show | jobs
by eongchen 111 days ago
This article is solving a problem that shouldn't exist in the first place. If you're loading 84 MCP tools into every session, the issue isn't MCP vs CLI, it's that you've turned on everything without thinking about when each tool is actually relevant.

MCP's token cost is the price of availability. The fix isn't to replace the protocol, it's to only activate the tools that matter for the current context. Claude's Skills already work this way -> lightweight descriptions loaded upfront, full definitions fetched on demand. That's essentially the same lazy-loading pattern CLIHub describes, just built into the model's native workflow.

1 comments

I go with this approach for all my personal tools and find it much easier to use and have CC or any LLM reason how to use the tools, and the added benefit that it has a super small footprint in context. https://gist.github.com/Shehryar/22059e16ba70a42fc72c13fde9f...